EP3734225A1 - Procédé de construction et de navigation cartographique, dispositif et système - Google Patents

Procédé de construction et de navigation cartographique, dispositif et système Download PDF

Info

Publication number
EP3734225A1
EP3734225A1 EP18893502.7A EP18893502A EP3734225A1 EP 3734225 A1 EP3734225 A1 EP 3734225A1 EP 18893502 A EP18893502 A EP 18893502A EP 3734225 A1 EP3734225 A1 EP 3734225A1
Authority
EP
European Patent Office
Prior art keywords
obstacle
type
map
navigation
building
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP18893502.7A
Other languages
German (de)
English (en)
Other versions
EP3734225A4 (fr
Inventor
Congbing LI
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZTE Corp
Original Assignee
ZTE Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by ZTE Corp filed Critical ZTE Corp
Publication of EP3734225A1 publication Critical patent/EP3734225A1/fr
Publication of EP3734225A4 publication Critical patent/EP3734225A4/fr
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3863—Structures of map data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G01C21/383—Indoor data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3863—Structures of map data
    • G01C21/387—Organisation of map data, e.g. version management or database structures
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas

Definitions

  • the present application relates to, but is not limited to, the field of data processing, for example, relates to a map building method, a navigation method, a device and a system.
  • a complete two-dimensional grid is used for abstractly representing the entire indoor environment information.
  • the rasters on the raster map are classified into three types, namely obstacle raster, non-obstacle raster and unknown raster.
  • the obstacle raster represents that an obstacle exists at a position corresponding to the obstacle raster
  • the non-obstacle raster represents that a position corresponding to the non-obstacle raster is free to pass
  • the unknown raster represents that information at a position corresponding to the unknown raster is unknown.
  • the traditional raster map building method all environment information is tightly coupled on the same raster map, and a navigation map at the current time is only used at the current time, so that the reusability is poor.
  • the influence of the raster where the obstacle is located on passage condition of the nearby rasters is not considered. Since a mobile robot itself occupies certain space, the robot cannot pass through the nearby rasters of the obstacle without limit. Otherwise, the robot is likely to collide with the obstacle while passing through the nearby rasters of the obstacle.
  • an improvement solution in the related art is that hierarchical management and updating mechanism of the raster map are introduced, and the raster map is divided into a static map layer, an obstacle map layer, a sonar obstacle map layer, an expansion map layer and so on from bottom to top.
  • the static map layer manages that the mobile robot moves in a room without interference of a dynamic obstacle.
  • the static map layer is a raster representation of the overall environment built according to information detected by a sensor.
  • the obstacle map layer is a raster representation of a dynamic obstacle detected by a laser sensor during the mobile robot performing a navigation task.
  • the sonar obstacle map layer is a raster representation of a dynamic obstacle detected by a sonar sensor during the mobile robot performing the navigation task.
  • the expansion map layer does not use data of an external sensor, and perform expansion process on peripheral non-obstacle rasters of the obstacle rasters with a predetermined expansion radius as a scale through using the respective obstacle rasters in the static map layer, the obstacle map layer, and the sonar map layer as fulcrums.
  • the non-obstacle rasters in the expansion radius form an expansion map layer.
  • the robot may pass when ensuring that a central point of the robot does not coincide with these non-obstacle rasters.
  • this map building method still has shortcomings in performance, such as in at least one of availability, flexibility, safety or resource utilization.
  • An embodiment of the present application provides a map building method.
  • the map building method includes following steps: identifying a detected obstacle, and determining a type of the obstacle according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic; building a map and marking the obstacle, and recording the type of the obstacle.
  • An embodiment of the present application further provides a map building system.
  • the map building system includes an obstacle identification unit, an obstacle classification unit and an obstacle processing unit.
  • the obstacle identification unit is configured to identify a detected obstacle to obtain an identification result.
  • the obstacle classification unit is configured to determine a type of the obstacle according to the identification result from multiple obstacle types obtained through classification according to an obstacle characteristic.
  • the obstacle processing unit is configured to build a map and mark the obstacle, and record the type of the obstacle.
  • An embodiment of the present application further provides a map building device.
  • the map building device includes a memory, a processor and computer programs stored in the memory and executable on the processor. When executing the computer programs, the processor implements the map building method described in the embodiment of the present application.
  • An embodiment of the present application further provides a computer storage medium.
  • Computer programs are stored in the computer storage medium.
  • the computer programs after read by a processor, execute the map building method described in the embodiment of the present application.
  • An embodiment of the present application further provides a navigation method.
  • the navigation method includes following steps: identifying a newly added obstacle detected on a path, and determining a type of the newly added obstacle according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic; performing an obstacle avoidance process according to the type of the newly added obstacle.
  • An embodiment of the present application further provides a navigation system.
  • the navigation system includes a navigation module and a map building module.
  • the navigation module is configured to plan a path, and notify the map building module of starting a navigation map update task.
  • the map building module is configured to identify a newly added obstacle detected on the path, and determine a type of the newly added obstacle according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic.
  • the navigation module is further configured to receive the updated navigation map, and perform obstacle avoidance process according to the type of the newly added obstacle.
  • An embodiment of the present application further provides a navigation device.
  • the navigation device includes a memory, a processor and computer programs stored in the memory and executable on the processor.
  • the processor implements the navigation method described in the embodiment of the present application.
  • An embodiment of the present application further provides a computer storage medium.
  • Computer programs are stored in the computer storage medium.
  • the computer programs after read by a processor, execute the navigation method described in the embodiment of the present application.
  • the obstacles are roughly classified according to detection results of a sensor such as a laser sensor or a sonar sensor, but rather than classified according to characteristics of identified obstacles themselves.
  • a sensor such as a laser sensor or a sonar sensor
  • semantics are weak, and it is hard to implement flexible map building and obstacle avoidance strategy according to the characteristics of the obstacles.
  • embodiments of the present application provide new map building and navigation solutions.
  • An embodiment relates to a map building method and a map building system.
  • the map building method in the embodiment is implemented by the map building system.
  • the map building system may be implanted into a navigation chip used by a mobile robot, and may be integrated with a visual sensor used by the mobile robot, or may be implemented by a single chip; the above is similar in other applications.
  • a map in the embodiment is an indoor raster map as an example, but the present application is not limited to this, and the manner of classifying obstacles may be extended to an outdoor map, a non-raster map and the like.
  • the map building method in the embodiment is shown in FIG. 1 , and includes step 110 and step 120.
  • a detected obstacle is identified, and a type of the obstacle is determined according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic.
  • the above obstacle characteristic refers to the characteristic of the obstacle itself, and before the type of the obstacle is determined, the obstacle needs to be identified first, for example, the obstacle is identified as a person, an animal, a television, a cabinet and the like.
  • the detection result For example, in the related art, it is detected whether the current obstacle moves within a period of time, and the obstacle is classified into a dynamic state or a static state according to a detection result. Such classification does not reflect the characteristic of the obstacle itself, nor can it determine whether the obstacle has an autonomous movement capability.
  • the obstacle characteristic includes at least one of autonomous movement capability, interaction capability, safety or autonomous avoidance capability of the obstacle.
  • the autonomous movement capability of the obstacle indicates that the obstacle itself can move without an external force applied to move the obstacle.
  • human, animal, a toy car and a mobile robot have the autonomous movement capability, but furniture such as a table, a chair and a sofa, and electric appliances such as a television do not have the autonomous movement capability.
  • the interaction capability of the obstacle refers to human-machine interaction capability, and includes, but is not limited to, voice interaction and gesture interaction. An adult or a mobile robot supporting interaction may fall into this category.
  • the mobile robot may also be considered as a special "human".
  • the safety of the obstacle refers to whether the obstacle is a protected object, such as an infant.
  • a user may also designate other items as the protected object.
  • the autonomous avoidance capability of the obstacle refers to whether autonomous avoidance of the obstacle can be implemented under a stress condition, for example, when the mobile robot gets close to the obstacle.
  • a specific object is classified, the above capabilities of the object may overlap.
  • an obstacle with the autonomous avoidance capability usually also has the autonomous movement capability, and so does the adult with human-machine interaction capability.
  • the multiple obstacle types obtained through classification according to the obstacle characteristic include at least two of a stabilization type, a negotiation type, a risk type or a violent-change type.
  • a stabilization type obstacle includes at least one obstacle without the autonomous movement capability.
  • a negotiation type obstacle includes at least one obstacle with the autonomous movement capability and the human-machine interaction capability.
  • a risk type obstacle includes at least one obstacle acted as the protected object.
  • a violent-change type obstacle includes at least one obstacle with the autonomous avoidance capability.
  • the stabilization type obstacle includes, but is not limited to, objects without the autonomous movement capability, such as wall, door, window, baby carriage, sofa, table, chair, cabinet and television, and the positions of these objects are relatively stable. Once these obstacles are marked on a raster map, the information on the raster map may be reused for a relatively long period of time.
  • the negotiation type obstacle includes humans with the autonomous movement capability and voice interaction capability other than infants.
  • the humans themselves have good behavior capability and good interaction capability, may actively adjust own behaviors according to external information, may provide more choices for autonomous navigation of the mobile robot, and enhance the flexibility of the mobile robot.
  • the risk type obstacle includes the protected objects such as infants, who are a crowd with weak autonomous behavior capability, weak voice interaction capability and weak risk recognition capability.
  • Such crowd are the objects that should be prevented and protected most during the autonomous navigation of the mobile robot. Safety of such crowd is more important than the efficiency of the autonomous navigation of the mobile robot.
  • the violent-change type obstacle includes, but is not limited to, a household pet with strong movement capability such as a cat and a dog, and electronic equipment with strong movement capability such as a robot. They all have the autonomous avoidance capability, and have good maneuverability and high randomness of movement.
  • the current image identification can identify more than 1000 kinds of articles, and most common obstacles in home environment can be identified. Unidentified obstacles may be classified as the stabilization type obstacles for processing, or may be classified as a separate type.
  • the multiple obstacle types obtained through classification according to the obstacle characteristic include at least two of the stabilization type, the negotiation type, the risk type or the violent-change type.
  • the stabilization type obstacle includes at least one of a building component or furniture.
  • the negotiation type obstacle includes an adult.
  • the risk type obstacle includes an infant.
  • the violent-change type obstacle includes a household pet.
  • the multiple obstacle types are also obtained through classification according to the obstacle characteristic, but it is not strictly required that articles being of a certain type have exactly at least one same characteristic.
  • not all obstacles in the environment need to be classified, only some important obstacles such as a building component, furniture, an adult, an infant and a household pet need to be classified. If at least two of an adult, an infant, a building component or a household pet are processed according to different strategies, the classification and recording are performed during building the map, that is, the method in the another embodiment is adopted.
  • the term "adult” refers to a healthy person with the autonomous movement capability and the human-machine interaction. Special adults who have disabled lower limbs or are deaf-mute may be classified separately, especially when the family members are relatively fixed. Certainly, the adults may not be classified in detail as above, and the special adults may also be classified as the negotiation type obstacles and a new route may be planned when no response is obtained during obstacle avoidance.
  • names of the above types of the obstacles may be changed.
  • the above four types may also be called as a first type, a second type, a third type and a fourth type, or other names capable of being distinguished as different types, and such name variations do not constitute any difference in the technical solution.
  • the process of identifying the detected obstacle, and determining the type of the obstacle according to the identification result from the multiple obstacle types obtained through classification according to the obstacle characteristic includes: performing obstacle detection on image information acquired by a visual sensor; performing image identification on an image of the detected obstacle; and searching information of preset obstacles respectively included in the multiple obstacle types according to the identified obstacle, to determine the type of the obstacle. For example, when a cat appears in an image acquired by the visual sensor, an image of the cat is extracted through the obstacle detection, and the cat is known to be a cat through the image identification. Among the preset obstacles included in the multiple obstacle types, the cat belongs to the violent-change type obstacle, so the type of the obstacle may be determined to be the violent-change type.
  • the above classification may be implemented through a classifier.
  • the type of the obstacle may be recorded either directly or indirectly.
  • the detected type is directly recorded as type identification in attribute information of the obstacle; or the obstacle is only marked on a layer corresponding to the type of the obstacle, and the type of the obstacle may be determined according to the layer where the obstacle is located.
  • the present application does not limit the manner of recording, as long as the recorded information may be used for determining the type of obstacle later.
  • step 120 a map is built and the obstacle is marked, and the type of the obstacle is recorded.
  • the map in the embodiment is a raster map.
  • the process in which the map is built and the obstacle is marked includes: building different map layers for obstacles which are of different types, and marking each of the obstacles on a map layer corresponding to a type of the each of the obstacles according to the type of the each of the obstacles.
  • the above built map is a navigation map
  • the identification, classification and marking of the obstacle are the identification, classification and marking of a newly added obstacle detected during the navigation in addition to an obstacle already existing on the environment map.
  • the map built according to the method in the embodiment may be also used for services other than the navigation.
  • the built map is a real-time dynamic scenario map used for services such as real environment game and scout. In this case, obstacles are not distinguished into original obstacle and newly added obstacle.
  • the navigation map in the embodiment is a navigation map including a static map layer.
  • the static map layer is marked with an obstacle already existing in the environment before navigation is performed.
  • the static map layer may be generated according to an introduced environment map.
  • An obstacle marked on the static map layer is the stabilization type obstacle.
  • the newly added obstacle detected in the environment is identified, a dynamic map layer is built and the newly added obstacle is marked, and the type of the newly added obstacle is recorded. After that, expansion process may be performed on a periphery of the obstacle, and the static map layer and the dynamic map layer are merged to obtain an updated navigation main map.
  • the navigation map may include map layers described below:
  • the stabilization type obstacle map layer is configured to maintain a newly added stabilization type obstacle detected by the visual sensor during the navigation of the mobile robot and not included on the static map layer.
  • the violent-change type obstacle map layer is configured to maintain the violent-change type obstacle detected by the visual sensor during the navigation of the mobile robot.
  • the negotiation type obstacle map layer is configured to maintain the negotiation type obstacle detected by the visual sensor during the navigation of the mobile robot.
  • the risk type obstacle map layer is configured to maintain the risk type obstacle detected by the visual sensor during the navigation of the mobile robot.
  • respective map layers are independent from each other and have respective clear semantics.
  • it is only necessary to merge the data of the respective map layers in an order.
  • the embodiment adopts at least one of strategies described below according to the type of the obstacle.
  • the process in which the map is built and the obstacle is marked includes: if the type of the obstacle is the violent-change type, building the violent-change type obstacle map layer and marking the obstacle.
  • a maintenance area of the violent-change type obstacle map layer is smaller than a maintenance area of a map layer other than the violent-change type obstacle map layer..
  • the map layer other than the violent-change type obstacle map layer is configured to mark an obstacle which is of a type other than the violent-change type in the multiple obstacle types. If the maintenance area is small, the built map is small.
  • the map layer other than the violent-change type obstacle map layer may be at least one of the stabilization type obstacle map layer, the risk type obstacle map layer or the negotiation type obstacle map layer.
  • the map layer other than the violent-change type obstacle map layer may be a map layer used for marking an obstacle being of other type.
  • the method further includes: performing an expansion process on a periphery of the obstacle. If the type of the obstacle is the risk type, a first expansion radius is utilized to perform the expansion process. The first expansion radius is greater than an expansion radius utilized to perform the expansion process on a periphery of an obstacle which is of a type other than the risk type in the multiple obstacle types.
  • the expansion process may be performed on the periphery of the obstacle on a current map layer according to a corresponding expansion radius before respective map layers are merged, and after the expansion process, the respective map layers are merged.
  • the expansion process may be performed after the merging, which is not limited in the present application.
  • the expansion strategy may be adopted on a map which is not layered.
  • a condition for sufficient expansion is met at the periphery of the risk type obstacle raster, that is, the expansion process of a predetermined range is performed in eight directions of the risk type obstacle, namely front, back, left, right, upper left, upper right, lower left and lower right, through taking the risk type obstacle raster as a center and taking a radical expansion radius as the scale.
  • a phenomenon of insufficient expansion occurs.
  • an obstacle avoidance condition is met beyond the expansion radius, that is, whether an obstacle-free raster that the robot can pass exists on a path between a current position and a target position.
  • the obstacle avoidance condition is met beyond the expansion radius, the mobile robot avoids the obstacle through a raster beyond the expansion radius and proceeds to the target point.
  • the condition for sufficient expansion is not met at the periphery rasters of the risk type obstacle, or the obstacle avoidance condition is not met beyond the expansion radius, it is indicated that the path is impassable or free space around the obstacle is not enough to ensure the requirement of safe navigation, and a new path needs to be planned to reach the target point.
  • the method further includes: adding the newly added stabilization type obstacle which is marked on the dynamic map layer onto the static map layer.
  • the stabilization type obstacle map layer is built and the newly added obstacle is marked. If the newly added obstacle is an obstacle being of other type, other dynamic map layer is built and the newly added obstacle is marked. In this example, after one navigation is completed, the newly added obstacle marked on the stabilization type obstacle map layer may be directly added onto the static map layer. However, in other examples, the stabilization type obstacle may be selected according to type information in the obstacle attribute and added onto the static map layer, and it is unnecessary to build an individual dynamic map layer for the newly added obstacle.
  • the position of the stabilization type obstacle in the environment may be changed, and if such change is not reflected on the static map, the accuracy of modeling of the environment map is affected.
  • the subsequent autonomous navigation may be affected.
  • the static map layer is updated and perfected according to the detected stabilization type obstacle, so that repeated processing of the stabilization type obstacle in a next navigation task is avoided, and the efficiency is improved. If the obstacle marked on the static map layer is in the current navigation, the static map layer may also be updated to delete the corresponding obstacle.
  • the embodiment further provides a map building system for implementing the above method.
  • the map building system is implanted into the navigation chip used by the mobile robot, and may be integrated with the visual sensor used by the mobile robot, or may be implemented by a single chip.
  • the chip or the visual sensor is connected to a robot control system.
  • the map building system in the embodiment includes an obstacle identification unit 10, an obstacle classification unit 20, an obstacle processing unit 30, an obstacle capturing unit 40, a map layer merging unit 50, an obstacle updating unit 60, a navigation map building interface 70, a static map building interface 80, a map updating interface 90 and a map storing interface 100.
  • the obstacle identification unit 10 is configured to identify the detected obstacle to obtain the identification result.
  • the obstacle classification unit 20 is configured to determine the type of the obstacle according to the identification result from multiple obstacle types obtained through classification according to the obstacle characteristic.
  • the obstacle processing unit 30 is configured to build the map and mark the obstacle, and record the type of the obstacle.
  • the obstacle characteristic includes at least one of autonomous movement capability, interaction capability, safety or autonomous avoidance capability of the obstacle.
  • the multiple obstacle types obtained through classification according to the obstacle characteristic include at least two of the stabilization type, the negotiation type, the risk type or the violent-change type.
  • the stabilization type obstacle includes at least one of a building component or furniture.
  • the negotiation type obstacle includes an adult.
  • the risk type obstacle includes an infant.
  • the violent-change type obstacle includes a household pet.
  • the built map is the raster map.
  • the obstacle processing unit is configured to build the map and mark the obstacle through following operations: building different map layers for obstacles which are of different types, and marking each of the obstacles on the map layer corresponding to the type of the each of the obstacles according to the type of the each of the obstacles.
  • the obstacle processing unit may specifically includes following sub-units: a violent-change type obstacle map layer processing unit, a risk type obstacle map layer processing unit, a negotiation type obstacle map layer processing unit and a stabilization type obstacle map layer processing unit.
  • the violent-change type obstacle map layer processing unit is configured to process the violent-change type obstacle and build the violent-change type obstacle map layer.
  • the risk type obstacle map layer processing unit is configured to process the risk type obstacle and build the risk type obstacle map layer.
  • the negotiation type obstacle map layer processing unit is configured to process the negotiation type obstacle and build the negotiation type obstacle map layer.
  • the stabilization type obstacle map layer processing unit is configured to process the stabilization type obstacle and build the stabilization type obstacle map layer. An obstacle not belonging to the violent-change type, the risk type and the negotiation type may also be processed by the stabilization obstacle map layer processing unit.
  • a filtering distance used by the violent-change type obstacle map layer processing unit when filtering obstacles is the smallest, and the filtering distance is equivalent to the size of the maintenance area of the map layer.
  • the respective map layer processing units may add different type values to obstacles on the respective layers.
  • the system further includes the obstacle capturing unit 40.
  • the obstacle capturing unit 40 is configured to perform obstacle detection according to the image information acquired by the visual sensor, that is, the obstacle capture unit 40 is configured to find the obstacle.
  • the obstacle identification unit is configured to identify the detected obstacle through a following operation: performing image identification on an image of the obstacle detected by the obstacle capturing unit.
  • the obstacle classification unit is configured to determine the type of the obstacle from the multiple obstacle types obtained through classification according to the obstacle characteristic through a following operation: searching information of preset obstacles respectively included in the multiple obstacle types according to the obstacle identified by the obstacle identification unit, to determine the type of the obstacle.
  • the obstacle capturing unit is optional.
  • the process of performing the obstacle detection according to the image information acquired by the visual sensor may be completed by the visual sensor or a subsequent function unit.
  • the operation in which the obstacle processing unit builds the map and marks the obstacle includes: if the type of the obstacle is the violent-change type, building the violent-change type obstacle map layer and marking the obstacle.
  • a maintenance area of the violent-change type obstacle map layer is smaller than a maintenance area of other map layer.
  • the other map layer is configured to mark an obstacle which is of a type other than the violent-change type in the multiple obstacle types.
  • the map is the navigation map including the static map layer.
  • the static map layer is marked with an obstacle already existing in the environment before the navigation is performed.
  • the obstacle identification unit is configured to identify the detected obstacle through a following operation: identifying a newly added obstacle detected in the environment during the navigation.
  • the operation in which the obstacle processing unit builds the map and marks the obstacle includes: building a dynamic map layer and marking the newly added obstacle.
  • the system further includes the map layer merging unit 50.
  • the map layer merging unit 50 is configured to perform an expansion process on a periphery of an obstacle, and merge the static map layer and the dynamic map layer to obtain the updated navigation main map.
  • the static map layer and the dynamic map layer are merged, that is, an obstacle marked in the static map layer and an obstacle marked in the dynamic map layer are marked in the same map according to positions of the obstacles, and a mapping relation among the obstacles, expansion rasters and map coordinates on the map is maintained.
  • Other related information such as an expansion range and the type of the obstacle is also stored in the associated data of the map.
  • the merging of the map layers is optional.
  • the above expansion strategy, reuse strategy and avoidance strategy may still be used through obstacle characteristic classification.
  • the expansion process on the obstacle is performed by a single function unit.
  • the multiple obstacle types include the risk type, and the risk type obstacle includes an infant.
  • the system further includes an obstacle expansion unit.
  • the obstacle expansion unit is configured to perform the expansion process on a periphery of an obstacle marked on the map, and when the type of the obstacle is the risk type, a first expansion radius is utilized to perform the expansion process.
  • the first expansion radius is greater than an expansion radius utilized to perform the expansion process on a periphery of an obstacle which is of a type other than the risk type in the multiple obstacle types.
  • the map is the navigation map including the static map layer.
  • the multiple obstacle types include the stabilization type.
  • the stabilization type obstacle includes at least one of a building component or furniture.
  • the system further includes the obstacle updating unit 60.
  • the obstacle updating unit 60 is configured to add the newly added stabilization type obstacle marked on the dynamic map layer onto the static map layer after the navigation is completed.
  • the above function units of the map building system are encapsulated into interfaces, so that the above function units become a service platform capable of providing a map service for a service such as the mobile robot service.
  • the above function units and the interfaces may be respectively implemented through discrete devices.
  • Interfaces of the map building system in the embodiment include a navigation map building interface 70.
  • the navigation map building interface 70 is configured to receive an external request for updating a navigation map, start the obstacle identification unit, the obstacle classification unit, the obstacle processing unit and the map layer merging unit to execute a navigation map updating task, and return an updated navigation main map to the mobile robot service.
  • the interfaces of the map building system may further include a static map building interface 80.
  • the static map building interface 80 is configured to receive an external request for building a static map, complete the building of an indoor environment static map and return the static map to the requester.
  • the static map layer may alternatively be implemented through introducing an environment map, and not necessarily be built by the map building system.
  • a map updating interface 90 is configured to receive an external request for updating a map, and add a newly added stabilization type obstacle marked on a dynamic map layer onto the static map layer after one navigation is completed.
  • a map storing interface 100 is configured to store the built or updated static map.
  • the static map may be updated and stored by itself.
  • the embodiment further provides a map building device.
  • the map building device includes a memory, a processor and computer programs stored in the memory and executable on the processor. When executing the computer programs, the processor implements the method in the embodiment.
  • the representation of the map is more semantic and refined, so that better practicability, flexibility and safety may be provided for the autonomous navigation of the mobile robot, and the resources may be saved.
  • the map building solution in the embodiments of the present application is very suitable for an application scenario of indoor mobile robot navigation.
  • An embodiment provides a navigation method. As shown in FIG. 3 , the navigation method includes step 210 and step 220.
  • a newly added obstacle detected on a path is identified, and a type of the newly added obstacle is determined according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic.
  • an obstacle avoidance process is performed according to the type of the newly added obstacle.
  • the multiple obstacle types obtained through classification according to the obstacle characteristic include a negotiation type and other types.
  • a negotiation type obstacle includes an adult.
  • the other types may be a stabilization type, a violent-change type and the like.
  • the other types are not limited.
  • the process in which the obstacle avoidance process is performed according to the type of the newly added obstacle includes: if the newly added obstacle is the negotiation type obstacle, interacting with the negotiation type obstacle to request avoidance of the negotiation type obstacle.
  • the method further includes: determining whether the negotiation type obstacle executes, in a preset duration, at least one operation of leaving the path or returning a response of agreeing to avoid; proceeding along the path based on a determination result that the negotiation type obstacle executes the at least one operation of (i) leaving the path or (ii) returning the response of agreeing to avoid; planning a new path based on a determination result that the negotiation type obstacle does not execute the at least one operation of leaving the path or returning the response of agreeing to avoid.
  • a navigation map used for navigation is an indoor raster map used by a mobile robot during the navigation.
  • the navigation map may be built according to the map building method in the embodiment 1, but this is not necessary, as long as the negotiation type obstacle may be distinguished from an obstacle being of other type in the built map.
  • the embodiment further provides a navigation system.
  • the navigation system includes a navigation module 101 and a map building module 102.
  • the navigation module 101 is configured to plan a path, and notify the map building module of starting a navigation map updating task.
  • the map building module 102 is configured to identify a newly added obstacle detected on the path, determine a type of the newly added obstacle according to an identification result from multiple obstacle types obtained through classification according to an obstacle characteristic, update the navigation map to mark the newly added obstacle and record the type of the newly added obstacle, and return the updated navigation map to the navigation module.
  • the navigation module 101 is further configured to receive the updated navigation map, and perform an obstacle avoidance process according to the type of the newly added obstacle.
  • the above navigation module may be implemented by, for example, a navigation system controlling the proceeding of the mobile robot, and the map building system may use, but is not limited to, the map building system described in the embodiment 1.
  • the multiple obstacle types include a negotiation type.
  • a negotiation type obstacle includes an adult.
  • the system further includes a human-machine interaction module.
  • the human-machine interaction module may be a voice system.
  • the navigation module is configured to perform the obstacle avoidance process according to the type of the newly added obstacle through a following operation: if the newly added obstacle is the negotiation type obstacle, interacting with the negotiation type obstacle through the human-machine interaction module to request avoidance of the negotiation type obstacle.
  • the navigation module is further configured to determine whether the negotiation type obstacle executes, in the preset duration, at least one operation of leaving the path or returning a response of agreeing to avoid; keep the path unchanged based on a determination result that the negotiation type obstacle executes the at least one operation of leaving the path or returning the response of agreeing to avoid; plan a new path based on a determination result that the negotiation type obstacle does not execute the at least one operation of leaving the path or returning the response of agreeing to avoid.
  • the type of the newly added obstacle classified according to the obstacle characteristic is determined during the navigation, and different obstacle avoidance strategies are adopted for obstacles being of different types, so that the obstacle avoidance effect is improved.
  • the embodiment describes, through an example, a raster map building procedure based on indoor obstacle characteristic classification.
  • a mobile robot moves around an indoor environment, and complete the building of a static map layer according to information of an external sensor. Since this stage occurs before the mobile robot navigation task, all obstacles in the static map layer are stabilization type obstacles.
  • the procedure includes step 301 to step 313.
  • a navigation task is started.
  • a map building system detects an image acquired by a sensor and finds that a new obstacle appears in front.
  • step 303 an image of the obstacle is identified.
  • the map building system performs feature extraction and feature identification according to image information of the obstacle, for example, the map building system identifies that the obstacle in front is a cat or a table.
  • the obstacle is classified.
  • the map building system classifies the obstacle according to the type of the obstacle.
  • step 305 it is determined whether the obstacle is a violent-change type obstacle. If the obstacle is the violent-change type obstacle, the procedure proceeds to the step 306; if the obstacle is not the violent-change type obstacle, the procedure proceeds to the step 307.
  • the obstacle is marked on a violent-change type obstacle map layer, and the procedure proceeds to the step 312.
  • a maintenance area of the violent-change type obstacle map layer is smaller than maintenance areas of other map layers.
  • step 307 it is determined whether the obstacle is a risk type obstacle.
  • the procedure proceeds to the step 308 based on a determination result that the obstacle is the risk type obstacle, or the procedure proceeds to the step 309 based on a determination result that the obstacle is not the risk type obstacle.
  • the obstacle is marked on a risk type obstacle map layer, and the procedure proceeds to the step 312.
  • step 309 it is determined whether the obstacle is a negotiation type obstacle.
  • the procedure proceeds to the step 310 based on a determination result that the obstacle is the negotiation type obstacle, or the procedure proceeds to the step 311 based on a determination result that the obstacle is not the negotiation type obstacle.
  • the obstacle is marked on a negotiation type obstacle map layer, and the procedure proceeds to the step 312.
  • the obstacle is marked on a stabilization type obstacle map layer.
  • step 312 all the above dynamic map layers and the static map layer are merged to obtain a main raster map used for navigation.
  • expansion process may be performed on peripheries of the obstacles.
  • An expansion radius used for the obstacle in the risk type obstacle map layer is greater than expansion radiuses used for obstacles in other map layers.
  • step 313 it is determined whether the navigation task is ended.
  • the procedure is ended based on a determination result that the navigation task is completed, or the procedure proceeds to the step 302 based on a determination result that the navigation task is not ended.
  • FIG. 6 to FIG. 11 A simple example of building map layers classified based on the obstacle characteristic is shown in FIG. 6 to FIG. 11 .
  • FIG. 6 shows an example of the static map layer.
  • the general distribution of the entire indoor environment is stored in rasters of this map layer.
  • the indoor environment is simplified, and if a raster range maintained by the map layer is from (0, 0) to (19, 19), only four stabilization type obstacles are included, and these obstacles are respectively located on coordinates (17, 0), (0, 4), (0, 19) and (19, 16).
  • FIG. 7 shows an example of the stabilization type obstacle map layer.
  • the stabilization type obstacle found during the navigation of the mobile robot is stored in the rasters of this map layer. It does not need to pay attention to the entire indoor environment space all the time, but only maintains the obstacle changes in a certain area in front of the sensor. For ease of understanding, it is assumed here that an area range where this map layer is responsible for maintaining is rasters with the size of 6 ⁇ 6, raster coordinates corresponding to the current maintenance area are from (3, 3) to (8, 8), and a stabilization type obstacle located at coordinates (6, 5) is newly found.
  • FIG. 8 shows an example of the negotiation type obstacle map layer.
  • the negotiation type obstacle found during the navigation of the mobile robot is stored in the rasters of this map layer. It does not need to pay attention to the entire indoor environment space all the time, but only maintains the obstacle changes in a certain area in front of the sensor. For ease of understanding, it is assumed here that an area range where this map layer is responsible for maintaining is rasters with the size of 6 ⁇ 6, raster coordinates corresponding to the current maintenance area are from (0, 0) to (5, 5), and a negotiation type obstacle located at coordinates (2, 1) is newly found.
  • FIG. 9 shows an example of the risk type obstacle map layer.
  • the risk type obstacle found during the navigation of the mobile robot is stored in the raster of this map layer. It does not need to pay attention to the entire indoor environment space all the time, but only maintains the obstacle changes in a certain area in front of the sensor.
  • an area range where this map layer is responsible for maintaining is a raster with the size of 6 ⁇ 6, raster coordinates corresponding to the current maintenance area are from (7, 7) to (12, 12), and a risk type obstacle located at a coordinate point (10, 9) is newly found.
  • FIG. 10 shows an example of the violent-change type obstacle map layer.
  • the violent-change type obstacle found during the navigation of the mobile robot is stored in the raster of this map layer. It does not need to pay attention to the entire indoor environment space all the time, but only maintains the obstacle changes in a certain area in front of the sensor.
  • an area range where this map layer is responsible for maintaining is rasters with the size of 3 ⁇ 3, raster coordinates corresponding to the current maintenance area are from (13, 13) to (15, 15), and a violent-change type obstacle located at coordinates (14, 14) is newly found.
  • FIG. 11 shows an example of the main raster map obtained after merging by the map layer merging unit.
  • This map layer extracts obstacles in each of the map layers, and arranges them on corresponding coordinates of the main raster map.
  • the expansion process is performed on peripheries of respective obstacles according to different expansion processing strategies. Specifically, the expansion process is performed on the periphery of the risk type obstacle using a radical expansion radius, and the expansion process is performed on the periphery of other obstacle using a conservative expansion radius. For simplicity, it is assumed that the radical expansion radius is 2 raster lengths and the conservative expansion radius is 1 raster length.
  • the map building system may update obstacle data of the stabilization type obstacle map layer to the static map layer.
  • the updated static map layer is shown in FIG. 12 .
  • a negotiation avoidance procedure in this embodiment includes step 401 to step 407.
  • step 401 during navigation of a mobile robot, an originally planned path is blocked due to appearance of a new obstacle in front.
  • a navigation system extracts type identification of the obstacle in a main raster map, determines that the obstacle is the negotiation type obstacle, and notifies a voice interaction service module of the mobile robot.
  • the voice interaction service module starts a voice interaction process, requests avoidance of the negotiation type obstacle in front, and waits for a response.
  • step 404 it is determined whether the negotiation type obstacle sends, in a preset duration, a positive voice response and takes an avoidance measure, and leaves the path.
  • the step 405 is executed based on a determination result that the negotiation type obstacle sends the positive voice response and takes the avoidance measure, and leaves the path.
  • the procedure proceeds to the step 406 based on a determination result that the negotiation type obstacle does not send the positive voice response, does not take the avoidance measure, and does not leave the path.
  • the step 405 may be executed when at least one condition of obtaining the positive voice response from the negotiation type obstacle or determining that the avoidance of the negotiation type obstacle has been performed is met.
  • the navigation system does not change the path, indicates the robot to normally follow the path to the target, and the procedure is ended.
  • the navigation system plans a new path by taking a current position of the mobile robot as a start point and taking the target point as an end point. If the new path is planned successfully, the step 407 is executed; if the new path is not planned successfully, it is indicated that no path capable of reaching the target point exists, the navigation task may be forcibly ended.
  • the navigation system indicates the mobile robot to reach the target point according to the new path, and the procedure is ended.
  • the raster map building system in this embodiment is packaged with various interfaces, and may provide a map service to the outside, which is called a raster map service platform in the embodiment.
  • the embodiment describes a process of calling the raster map service platform by a mobile robot service, and a third-party mobile robot service may be another application scenario established on the basis of autonomous navigation of an indoor robot.
  • the autonomous navigation is a basic function, and doing what after navigating to a target point may create value is a problem solved by the third-party mobile robot service.
  • the procedure includes steps described below.
  • the third-party mobile robot service calls a static map building interface provided by the raster map service platform, and starts a map building task.
  • the raster map service platform starts a map real-time building process and returns a map real-time building interface to the third-party mobile robot service.
  • the third-party mobile robot service drives the mobile robot moves around an indoor environment.
  • the third-party mobile robot service sends indoor environment information scanned by a sensor to the static map building interface of the raster map service platform.
  • the raster map service platform updates the map and sends the updated map to the third-party mobile robot service through the static map building interface, and a map interface is updated and presented in real-time.
  • step 6 the step 3 to step 5 are repeated until the indoor environment map is built, and the third-party mobile robot service calls a map storing interface of the raster map service platform to store the built map.
  • a storage process is started through the map storing interface, and the built map data is stored as a map file in an external memory.
  • a completed state is returned to the third-party mobile robot service through the map storing interface.
  • step 9 the third-party mobile robot executes the autonomous navigation, the above stored map file is loaded into the navigation system, and the map updating task is started through calling the navigation map building interface provided by the raster map service platform.
  • the navigation map building interface executes the process, a stabilization type obstacle map layer processing unit, a negotiation type obstacle map layer processing unit, a violent-change type obstacle map layer processing unit, a risk type obstacle map layer processing unit and a map layer merging unit are respectively started and configured to build the map layers corresponding to obstacles being of various types during the navigation of the mobile robot, and generate a main map.
  • a step 11 the obtained main raster map used for real-time navigation is returned to the third-party mobile robot service through the navigation map building interface.
  • the third-party mobile robot service uses the main raster map used for the real-time navigation for executing the navigation and other service tasks.
  • the third-party mobile robot service completes the navigation task at the current time and calls the map updating interface of the raster map service platform to update the static layer map.
  • a step 14 the process is executed by the map updating interface, and the static map layer is updated through using information of the stabilization type obstacle map layer.
  • the map updating interface exports the updated map, substitutes the original map file, returns the updated state to the third-party mobile robot service, and the entire procedure is ended.
  • function modules/units in all or part of the steps of the method, the system and the apparatus disclosed above may be implemented as software, firmware, hardware and appropriate combinations thereof.
  • the division of the function modules/units mentioned in the above description may not correspond to the division of physical components.
  • one physical component may have several functions, or one function or step may be implemented jointly by several physical components.
  • Some or all components may be implemented as software executed by processors such as central processing units, digital signal processors or microcontrollers, hardware, or integrated circuits such as application specific integrated circuits.
  • processors such as central processing units, digital signal processors or microcontrollers, hardware, or integrated circuits such as application specific integrated circuits.
  • Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transitory medium).
  • the term, computer storage medium includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data).
  • the computer storage medium includes, but is not limited to, a random-access memory (RAM), a Read-Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a flash memory, or other memory technologies, a Compact Disc Read-Only Memory (CD-ROM), a Digital Video Disc (DVD) or other optical disc storage, a magnetic cassette, a magnetic tape, disk storage or other magnetic storage apparatuses, or any other medium used to store the desired information and accessible by a computer.
  • the communication medium generally includes computer-readable instructions, data structures, program modules or other data in modulated data signals such as carriers or other transmission mechanisms, and may include any information delivery medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Navigation (AREA)
EP18893502.7A 2017-12-29 2018-12-24 Procédé de construction et de navigation cartographique, dispositif et système Pending EP3734225A4 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711499191.0A CN108344414A (zh) 2017-12-29 2017-12-29 一种地图构建、导航方法及装置、***
PCT/CN2018/123164 WO2019128933A1 (fr) 2017-12-29 2018-12-24 Procédé de construction et de navigation cartographique, dispositif et système

Publications (2)

Publication Number Publication Date
EP3734225A1 true EP3734225A1 (fr) 2020-11-04
EP3734225A4 EP3734225A4 (fr) 2022-01-26

Family

ID=62961303

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18893502.7A Pending EP3734225A4 (fr) 2017-12-29 2018-12-24 Procédé de construction et de navigation cartographique, dispositif et système

Country Status (4)

Country Link
US (1) US11359930B2 (fr)
EP (1) EP3734225A4 (fr)
CN (1) CN108344414A (fr)
WO (1) WO2019128933A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113156949A (zh) * 2021-04-19 2021-07-23 深圳市云鼠科技开发有限公司 机器人航向角纠偏方法、装置、计算机设备及存储介质

Families Citing this family (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108344414A (zh) * 2017-12-29 2018-07-31 中兴通讯股份有限公司 一种地图构建、导航方法及装置、***
CN109238296B (zh) * 2018-08-16 2022-03-22 佛山科学技术学院 一种高精度室内导航方法及装置
CN110895409B (zh) * 2018-08-23 2020-11-27 珠海格力电器股份有限公司 避让障碍物的控制方法
CN110928282A (zh) * 2018-09-17 2020-03-27 格力电器（武汉）有限公司 清扫机器人的控制方法及装置
CN108827336A (zh) * 2018-09-26 2018-11-16 广东工业大学 一种基于无人驾驶的路径规划方法、装置及设备
CN110968083B (zh) * 2018-09-30 2023-02-10 科沃斯机器人股份有限公司 栅格地图的构建方法、避障的方法、设备及介质
CN109568093A (zh) * 2018-11-27 2019-04-05 湖北经济学院 一种步行安全综合管理***及方法
CN109655073B (zh) * 2018-12-06 2021-07-23 宁波吉利汽车研究开发有限公司 一种在无或弱信号区域中的地图绘制方法、装置及车辆
CN111443695A (zh) * 2018-12-28 2020-07-24 珠海市一微半导体有限公司 扫地机器人控制方法、装置、存储介质及扫地机器人
CN111374607A (zh) * 2018-12-29 2020-07-07 尚科宁家(中国)科技有限公司 一种基于扫地机器人的目标识别方法及装置、设备、介质
CN109602343A (zh) * 2019-01-10 2019-04-12 珠海格力电器股份有限公司 基于微波雷达的扫地机器人的控制方法及装置、***
CN111624989B (zh) * 2019-02-28 2023-05-26 科沃斯机器人股份有限公司 控制方法及自移动设备
CN110081893B (zh) * 2019-04-01 2020-09-25 东莞理工学院 一种基于策略重用和强化学习的导航路径规划方法
US11429110B1 (en) * 2019-05-24 2022-08-30 Amazon Technologies, Inc. System for obstacle avoidance by autonomous mobile device
CN110164288A (zh) * 2019-06-04 2019-08-23 浙江大学昆山创新中心 一种基于自建图的静态地图在线更新方法和装置
US20220343241A1 (en) * 2019-06-21 2022-10-27 Intel Corporation Technologies for enabling collective perception in vehicular networks
CN112256005B (zh) * 2019-07-02 2022-11-15 广州哨马智能装备科技有限公司 基于超声波传感器的避障***和方法以及机器人
CN110522359B (zh) * 2019-09-03 2021-09-03 深圳飞科机器人有限公司 清洁机器人以及清洁机器人的控制方法
CN110658819B (zh) * 2019-09-30 2022-04-15 北京猎户星空科技有限公司 一种避障方法、装置、电子设备和存储介质
CN110764110B (zh) * 2019-11-12 2022-04-08 深圳创维数字技术有限公司 路径导航方法、装置及计算机可读存储介质
CN110736465B (zh) * 2019-11-15 2021-01-08 北京云迹科技有限公司 导航方法、装置、机器人及计算机可读存储介质
CN111060116B (zh) * 2019-12-04 2023-07-18 江西洪都航空工业集团有限责任公司 一种基于视觉的草场自主建图***
CN111338384B (zh) * 2019-12-17 2021-06-08 北京化工大学 一种仿蛇机器人自适应路径跟踪方法
CN111338336B (zh) * 2020-02-11 2021-07-13 腾讯科技（深圳）有限公司 一种自动驾驶方法及装置
CN111481105A (zh) * 2020-04-20 2020-08-04 北京石头世纪科技股份有限公司 一种自行走机器人避障方法、装置、机器人和存储介质
CN111631650B (zh) * 2020-06-05 2021-12-03 上海黑眸智能科技有限责任公司 基于障碍物高度检测的室内平面图生成方法、***、终端以及扫地机器人
CN111829526B (zh) * 2020-07-23 2022-05-10 中国人民解放军国防科技大学 一种基于防撞半径的距离地图重构与跳点路径规划方法
CN111966097B (zh) * 2020-08-12 2024-06-14 深圳华芯信息技术股份有限公司 基于栅格地图区域化探索的建图方法、***以及终端
CN112161624A (zh) * 2020-09-11 2021-01-01 上海高仙自动化科技发展有限公司 标记方法、标记装置、智能机器人及可读存储介质
CN112150491B (zh) * 2020-09-30 2023-08-18 北京小狗吸尘器集团股份有限公司 图像检测方法、装置、电子设备和计算机可读介质
CN112150490B (zh) * 2020-09-30 2024-02-02 北京小狗吸尘器集团股份有限公司 图像检测方法、装置、电子设备和计算机可读介质
CN112197763B (zh) * 2020-09-30 2024-02-27 灵动科技（北京）有限公司 地图构建方法、装置、设备和存储介质
CN112462768B (zh) * 2020-11-25 2024-03-29 深圳拓邦股份有限公司 移动机器人导航地图的创建方法、装置及移动机器人
CN112506204B (zh) * 2020-12-17 2022-12-30 深圳市普渡科技有限公司 机器人遇障处理方法、装置、设备和计算机可读存储介质
CN114691701A (zh) * 2020-12-31 2022-07-01 华为技术有限公司 高精度地图更新方法及装置
US11960282B2 (en) * 2021-01-05 2024-04-16 Abb Schweiz Ag Systems and methods for servicing a data center using autonomous vehicle
CN112904841B (zh) * 2021-01-12 2023-11-03 北京布科思科技有限公司 非水平朝向的单线定位避障方法和装置、设备及存储介质
CN112882470A (zh) * 2021-01-14 2021-06-01 中广核工程有限公司 一种核电站试验机器人及试验方法
KR20220121483A (ko) * 2021-02-25 2022-09-01 엘지전자 주식회사 지능적 맵 생성 방법 및 그 이동 로봇
CN113390417A (zh) * 2021-06-25 2021-09-14 深圳市优必选科技股份有限公司 机器人及其导航方法、装置和计算机可读存储介质
CN115687541A (zh) * 2021-07-21 2023-02-03 华为技术有限公司 一种地图、地图生成方法及装置
CN113485368B (zh) * 2021-08-09 2024-06-07 国电南瑞科技股份有限公司 一种架空输电线路巡线机器人导航、巡线方法及装置
CN113670292B (zh) * 2021-08-10 2023-10-20 追觅创新科技(苏州)有限公司 地图的绘制方法和装置、扫地机、存储介质、电子装置
CN113867349B (zh) * 2021-09-28 2024-04-09 浙江大华技术股份有限公司 一种机器人的避障方法、***及智能机器人
CN114003036A (zh) * 2021-10-28 2022-02-01 广州赛特智能科技有限公司 机器人避障控制方法、装置、设备和介质
CN114296447B (zh) * 2021-12-07 2023-06-30 北京石头世纪科技股份有限公司 自行走设备的控制方法、装置、自行走设备和存储介质
CN114185353B (zh) * 2021-12-09 2024-03-22 吉林大学 一种自主作业装载机倒车避障与路径规划方法
CN114415659B (zh) * 2021-12-13 2024-05-28 烟台杰瑞石油服务集团股份有限公司 一种机器人安全避障方法、装置、机器人及存储介质
DE102021133614A1 (de) * 2021-12-17 2023-06-22 Still Gesellschaft Mit Beschränkter Haftung Verfahren zur Erzeugung einer Umgebungskarte für einen mobilen Logistik-Roboter und mobiler Logistik-Roboter
CN115629612A (zh) * 2022-12-19 2023-01-20 科大讯飞股份有限公司 一种避障方法、装置、设备及存储介质
CN116466723A (zh) * 2023-04-26 2023-07-21 曲阜师范大学 一种消杀机器人避障方法、***和设备

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8989972B2 (en) 2008-09-11 2015-03-24 Deere & Company Leader-follower fully-autonomous vehicle with operator on side
JP5891553B2 (ja) * 2011-03-01 2016-03-23 株式会社国際電気通信基礎技術研究所 ルートパースペクティブモデル構築方法およびロボット
JP2014197294A (ja) * 2013-03-29 2014-10-16 株式会社日立産機システム 位置同定装置、及びそれを備えた移動ロボット
CN103984037B (zh) * 2014-04-30 2017-07-28 深圳市墨克瑞光电子研究院 基于视觉的移动机器人障碍物检测方法和装置
CN104615138B (zh) * 2015-01-14 2017-09-08 上海物景智能科技有限公司 一种划分移动机器人室内区域动态覆盖方法及其装置
CN104808671B (zh) * 2015-05-19 2017-03-15 东南大学 一种家居环境下的机器人路径规划方法
CN105182979B (zh) * 2015-09-23 2018-02-23 上海物景智能科技有限公司 一种移动机器人障碍物检测及避让方法和***
KR102521493B1 (ko) * 2015-10-27 2023-04-14 삼성전자주식회사 청소 로봇 및 그 제어방법
US9612123B1 (en) * 2015-11-04 2017-04-04 Zoox, Inc. Adaptive mapping to navigate autonomous vehicles responsive to physical environment changes
US10414052B2 (en) * 2016-02-09 2019-09-17 Cobalt Robotics Inc. Building-integrated mobile robot
US10816654B2 (en) * 2016-04-22 2020-10-27 Huawei Technologies Co., Ltd. Systems and methods for radar-based localization
US10730512B2 (en) * 2016-05-06 2020-08-04 Pcms Holdings, Inc. Method and system for collaborative sensing for updating dynamic map layers
CN106338996B (zh) * 2016-10-20 2019-05-31 上海物景智能科技有限公司 一种移动机器人安全控制的方法及***
CN106530946A (zh) * 2016-11-30 2017-03-22 北京贝虎机器人技术有限公司 用于编辑室内地图的方法及装置
KR102012550B1 (ko) * 2017-02-20 2019-08-20 엘지전자 주식회사 돌발 장애물을 식별하는 방법 및 이를 구현하는 로봇
US10907974B2 (en) * 2017-04-17 2021-02-02 Cisco Technology, Inc. Real-time updates to maps for autonomous navigation
WO2018218149A1 (fr) * 2017-05-26 2018-11-29 Google Llc Système de fusion de données
CN107256019B (zh) * 2017-06-23 2018-10-19 杭州九阳小家电有限公司 一种清洁机器人的路径规划方法
JP7062892B2 (ja) * 2017-07-13 2022-05-09 トヨタ自動車株式会社 ダイナミックマップ更新装置、ダイナミックマップ更新方法、ダイナミックマップ更新プログラム
US11562524B2 (en) 2017-10-31 2023-01-24 Hewlett-Packard Development Company, L.P. Mobile robots to generate occupancy maps
US10606269B2 (en) * 2017-12-19 2020-03-31 X Development Llc Semantic obstacle recognition for path planning
CN108344414A (zh) * 2017-12-29 2018-07-31 中兴通讯股份有限公司 一种地图构建、导航方法及装置、***

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113156949A (zh) * 2021-04-19 2021-07-23 深圳市云鼠科技开发有限公司 机器人航向角纠偏方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
US20200340826A1 (en) 2020-10-29
CN108344414A (zh) 2018-07-31
US11359930B2 (en) 2022-06-14
WO2019128933A1 (fr) 2019-07-04
EP3734225A4 (fr) 2022-01-26

Similar Documents

Publication Publication Date Title
US11359930B2 (en) Map construction and navigation method, and device and system
Guerrero-Higueras et al. Tracking people in a mobile robot from 2d lidar scans using full convolutional neural networks for security in cluttered environments
EP3683730A1 (fr) Procédé et système d'apprentissage dynamique de robot, robot et serveur en nuage
Basso et al. Fast and robust multi-people tracking from RGB-D data for a mobile robot
US11842446B2 (en) VR scene and interaction method thereof, and terminal device
KR20170087303A (ko) 출퇴근을 모니터링하기 위한 방법, 시스템 및 비일시성의 컴퓨터 판독 가능 기록 매체
WO2020015682A1 (fr) Système et procédé de commande d'un véhicule aérien sans pilote
CN115393386B (zh) 三维场景图的生成方法、装置、设备及可读存储介质
WO2021237448A1 (fr) Procédé, appareil et système de planification de trajet
CN113420708A (zh) 宠物看护方法、装置、电子设备及存储介质
Fernández-Chaves et al. ViMantic, a distributed robotic architecture for semantic mapping in indoor environments
WO2021248857A1 (fr) Procédé et système de discrimination d'attribut d'obstacle et robot intelligent
CN111343696A (zh) 自移动设备的通信方法、自移动设备及存储介质
CN111898557B (zh) 自移动设备的地图创建方法、装置、设备及存储介质
CN115546237A (zh) 点云密度调整方法、电子设备及存储介质
CN111854757A (zh) 导航方法、装置、电子设备及存储介质
CN114873389B (zh) 机器人确定自身楼层方法及相关设备
KR102103399B1 (ko) 인공지능 기반 사물인식을 활용한 가상 증강정보 제공 시스템 및 그 방법
Almonfrey et al. A flexible human detection service suitable for Intelligent Spaces based on a multi-camera network
US11967157B2 (en) Robot and method for controlling thereof
US20230367319A1 (en) Intelligent obstacle avoidance method and apparatus based on binocular vision, and non-transitory computer-readable storage medium
CN111881246B (zh) 一种用户移动数据的处理方法及装置
CN112597910B (zh) 利用扫地机器人对人物活动进行监控的方法和装置
JP2019139497A (ja) 画像処理システム及び画像処理方法
CN112465987A (zh) 一种视觉融合信息三维重建的导航地图构建方法

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20200729

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
RIC1 Information provided on ipc code assigned before grant

Ipc: G01C 21/20 20060101AFI20210826BHEP

A4 Supplementary search report drawn up and despatched

Effective date: 20220105

RIC1 Information provided on ipc code assigned before grant

Ipc: G01C 21/20 20060101AFI20211222BHEP

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20230803